Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    AI hook

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лү
    0.86
    Año
    0.85
    лық
    0.83
     ҡ
    0.79
     кы
    0.79
    Πα
    0.77
     кү
    0.77
     Pued
    0.75
    Ability
    0.75
    Ы
    0.75
    POSITIVE LOGITS
    isen
    0.69
     momenta
    0.68
     बदले
    0.68
    fficial
    0.67
    رير
    0.67
    renders
    0.66
    cline
    0.66
    elde
    0.66
     renders
    0.65
    риз
    0.64
    Act Density 0.001%

    No Known Activations